Rodrigo Arias rarias
  • Joined on 2024-04-26
rarias opened issue rarias/jungle#77 2024-08-30 12:04:44 +02:00
Enable nix cache server
rarias commented on issue rarias/jungle#76 2024-08-28 13:14:34 +02:00
Ceph OSDs not starting due condition not met

Right...

lake2% ls /dev/nvme*
/dev/nvme0  /dev/nvme0n1  /dev/nvme1  /dev/nvme1n1  /dev/nvme2  /dev/nvme2n1  /dev/nvme3  /dev/nvme3n1

Now ceph is working fine. Closing.

rarias closed issue rarias/jungle#76 2024-08-28 13:14:34 +02:00
Ceph OSDs not starting due condition not met
rarias commented on issue rarias/jungle#76 2024-08-28 13:08:50 +02:00
Ceph OSDs not starting due condition not met

Let's see if rebooting makes the disk appear again.

rarias opened issue rarias/jungle#76 2024-08-28 12:58:50 +02:00
Ceph OSDs not starting due condition not met
rarias opened issue rarias/jungle#75 2024-08-28 12:14:23 +02:00
DRAM errors in lake2
rarias commented on issue rarias/jungle#71 2024-08-02 11:35:11 +02:00
Prepare August automatic shutdown

All machines are off except hut, so we can check they were off.

image

image

I'll…

rarias opened issue rarias/jungle#74 2024-07-30 16:11:43 +02:00
Shutdown machines on high temperature
rarias commented on issue rarias/jungle#73 2024-07-23 16:42:17 +02:00
Cached and shared filesystem

With the following mount points:

hut% mount 
rarias opened issue rarias/jungle#73 2024-07-23 12:48:19 +02:00
Cached and shared filesystem
rarias pushed to update-nixos at rarias/jungle 2024-07-22 14:07:48 +02:00
0a8db8bda6 Set the serial console to ttyS1 in raccoon
dfc44d2be6 Remove setLdLibraryPath and driSupport options
Compare 2 commits »
rarias closed pull request rarias/jungle#66 2024-07-22 12:22:34 +02:00
Draft: Mount the nix store from hut in compute nodes
rarias created pull request rarias/jungle#72 2024-07-22 12:19:03 +02:00
Update NixOS and other changes
rarias pushed to update-nixos at rarias/jungle 2024-07-22 12:18:26 +02:00
f9970c0ac7 Add documentation section about GRUB chain loading
rarias created branch update-nixos in rarias/jungle 2024-07-22 11:54:39 +02:00
rarias pushed to update-nixos at rarias/jungle 2024-07-22 11:54:39 +02:00
4a52970821 Add 10 min shutdown jitter to avoid spikes
7b58d8fbcc Don't mount the nix store in owl nodes
f3167c0cc0 Emulate other architectures in owl nodes too
d3489f8e48 Program shutdown for August 2nd for all machines
86f5bea6c7 Enable debuginfod daemon in owl nodes
Compare 10 commits »
rarias commented on issue rarias/jungle#71 2024-07-22 11:49:36 +02:00
Prepare August automatic shutdown
owl1	OK
owl2	OK
hut		OK
eudy
koro	(no need)
lake2	OK
bay		OK
raccoon
xeon06	OK
hut% for host in {owl1,owl2,hut,lake2,bay}; do ssh $host echo '$(hostname)\\t$(systemctl…
rarias opened issue rarias/jungle#71 2024-07-19 18:06:05 +02:00
Prepare August automatic shutdown
rarias commented on issue rarias/jungle#70 2024-07-19 17:37:26 +02:00
Node owl2 reaches high temperatures due to slow fans

Setting it to performance, makes the fans stay at 10000 RPM and the temperature is fine under load:

image

rarias commented on issue rarias/jungle#70 2024-07-19 17:11:16 +02:00
Node owl2 reaches high temperatures due to slow fans

So, this seems to be the problem:

/------------------------------------------------------------------------------\